Early Detection of Seasonal Outbreaks from Twitter Data Using Machine Learning Approaches

Table 1

Relevant research studies on outbreak detection using machine learning approaches.

Research study	Year	Model	Disease type	Data sources	Objectives	Future work
Y. Wang et al. [18]	2020	PDE	Influenza flu	Twitter	To predict influenza or flu trend based on real-time data from OSM data.	In future work, this systematic approach will be extended to other types of an outbreak.
J. S. Coberly et al. [26]	2014	SVM	Dengue	Twitter	This study proposed a method that focused on geographic information about dengue fever. To associate the new case of dengue in a region with the reported cases by public health departments in the Philippines.	Overall tweet must be processed to achieve better insight into text data.
A. Alessa et al. [27]	2019	Linear regression	Flu, ILI	Twitter, CDC	This work aimed to develop an effective and accurate technique that efficiently utilizes OSM data to monitor the flu outbreak. To offer early detection, even for a novel epidemic.	There is a need for manual annotation to train the model for the entire OSM data.
K. Espina et al. [28]	2017	SVM, regression	Dengue, typhoid fever	Twitter	The purpose of the study is to strengthen the existing efforts to track disease outbreaks. This work has shown several dengue cases and typhoid fever in the Philippines to identify health-related tweets.	The work can be extended by exploring advanced machine learning techniques.
C. de a et al. [5]	2017	Linear regression	Dengue	Twitter	The key innovation of this work is to determine the importance of tweets regularly at the country and state level in Brazil for the fast detection and monitoring of a dengue outbreak.	Instead of traditional machine learning techniques, this work can be improved by utilizing deep learning techniques.
L. Sousa et al. [29]	2018	Naïve bayes, SVM	Dengue, chikungunya, zika	Twitter	To propose a VazaDengue system to detect mosquito-borne disease in tweets. To report and visualize new incidence of outbreaks.	In the future, there is a need to utilize Instagram content such as the classification of image data associated with the relevant post.
L. Chen et al. [19]	2016	Topic, hidden Markov model	Flu	Twitter	This work proposed syndromic surveillance of flu outbreak in tweets. To predict the flu outbreak, temporal topic models were deployed in this work.	In future work, the proposed state transition probabilities can be utilized for traditional epidemiological approaches.